© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9347
    Prev
    Next
    INDEX
    Explanations

    the word "self" preceding words related to personal qualities or questionnaires

    oai_token-act-pair · gemini-2.0-flash

    self

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     self
    -2.89
     Self
    -2.48
    self
    -2.47
    Self
    -2.45
     SELF
    -2.23
    SELF
    -2.00
     Selbst
    -1.72
    Selbst
    -1.56
     selves
    -1.50
    自我
    -1.45
    POSITIVE LOGITS
    DoubleQuotes
    0.66
    
    0.66
     CreateTagHelper
    0.66
    ViewFeatures
    0.66
    raulic
    0.57
    
    0.57
    TableHead
    0.56
     pauper
    0.54
     surla
    0.54
     laboral
    0.53
    Activations Density 2.223%

    No Known Activations